Qwen3.5 2B
Qwen3.5 2B is a lightweight 2 billion parameter dense model designed for efficient deployment while keeping multimodal vision-language capability, built on a hybrid architecture that pairs Gated DeltaNet with attention layers. It supports a 262,144 token native context window and runs in non-thinking mode by default for faster responses. Reported results include MMLU-Pro 55.3 and MMMU 64.2, with the model handling text, image, and video inputs across more than 200 languages. Thinking mode can be enabled when a task calls for step-by-step reasoning. Its small footprint makes it well suited to prototyping, task-specific fine-tuning, and resource-constrained scenarios where a compact multimodal model is preferred.
Key info
Benchmarks
Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.
Available routes
No routes currently available — Qwen3.5 2B isn't routed through the Opper gateway right now. It may return.
Contact us about this model →